Author(s) :

A.S.N.V Bhogesh.

Volume/Issue :

Abstract :

Spam detection plays a vital role in preventing the spread of unwanted and potentially harmful messages. This study explores the use of the Multinomial Naive Bayes (MultinomialNB) algorithm for effective text-based spam filtering. Leveraging its simplicity and efficiency, the MultinomialNB model achieved an exceptional 99% accuracy on a well-labeled dataset, showcasing its ability to distinguish between spam and legitimate messages with high precision. Its lightweight computational requirements make it well-suited for real-time spam filtering applications. Future work could explore expanding this approach to multi-modal spam filtering and integrating it with advanced machine learning techniques for improved scalability and adaptability.

No. of Downloads :

0